Study Background
♦ Hepatitis B virus (HBV) infection is associated with progression tocirrhosis, development of hepatocellular carcinoma, and liver-related
mortality
♦ Although most patients with HBV on suppressive antiviral therapy
achieve regression of cirrhosis, a subset do not; histologic features
associated with regression of cirrhosis are not well understood
♦ Image analysis methods have been applied to evaluate liver histology
in HBV; a machine learning (ML) approach leveraging convolutional
neural networks (CNNs) could facilitate characterization of histologic
features associated with regression of cirrhosis Juyal et al.
